4 accepted papers
Identifying meaningful latent representations within diffusion models remains a challenging problem for causal approaches. We propose Causal Manifold Transport Diffusion Model (CMT-Diff), a framework that operationalizes causal actions as geometric transformations. By adopting the perspective of bac
Text-guided image editing requires more than prompt following—it demands a principled understanding of what to modify versus what to preserve. We investigate the internal guidance mechanism of diffusion models and reveal that the guidance signal follows a structured semantic hierarchy. We formalize…
Recent progress in artificial intelligence has encouraged numerous attempts to understand and decode human visual system from brain signals. These prior works typically align neural activity independently with semantic and perceptual features extracted from images using pre-trained vision models. Ho
Vision-language models have achieved remarkable performance across various tasks by leveraging large-scale multimodal training data. However, their ability to generalize to out-of-distribution (OOD) domains requiring expert-level knowledge remains an open challenge. To address this, we investigate c